app.py

import os
import logging
from dotenv import load_dotenv
import streamlit as st
from PyPDF2 import PdfReader
from langchain.text_splitter import CharacterTextSplitter
from langchain_community.embeddings import HuggingFaceInstructEmbeddings
from langchain.vectorstores import FAISS
from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain
from langchain_groq import ChatGroq

# Load environment variables
load_dotenv()

# Set up logging
logging.basicConfig(
    level=logging.INFO,
    format='%(asctime)s - %(levelname)s - %(message)s'
)

# Function to extract text from PDF files
def get_pdf_text(pdf_docs):
    text = ""
    for pdf in pdf_docs:
        try:
            pdf_reader = PdfReader(pdf)
            for page in pdf_reader.pages:
                text += page.extract_text() or ""
        except Exception as e:
            st.warning(f"Could not read {pdf.name}. Skipping this file.")
            logging.warning(f"Error processing {pdf.name}: {e}")
    return text

# Function to split the extracted text into chunks
def get_text_chunks(text):
    text_splitter = CharacterTextSplitter(
        separator="\n",
        chunk_size=1000,
        chunk_overlap=200,
        length_function=len
    )
    chunks = text_splitter.split_text(text)
    return chunks

# Function to create a FAISS vectorstore
def get_vectorstore(text_chunks):
    embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
    vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
    return vectorstore

# Function to set up the conversational retrieval chain
def get_conversation_chain(vectorstore):
    try:
        groq_api_key = os.getenv("GROQ_API_KEY")
        llm = ChatGroq(model="llama-3.3-70b-versatile", temperature=0.5, api_key=groq_api_key)
        memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)
        
        conversation_chain = ConversationalRetrievalChain.from_llm(
            llm=llm,
            retriever=vectorstore.as_retriever(),
            memory=memory
        )
        
        logging.info("Conversation chain created successfully.")
        return conversation_chain
    except Exception as e:
        logging.error(f"Error creating conversation chain: {e}")
        st.error("An error occurred while setting up the conversation chain.")

# Handle user input
def handle_userinput(user_question):
    if st.session_state.conversation is not None:
        response = st.session_state.conversation({'question': user_question})
        st.session_state.chat_history = response['chat_history']

        for i, message in enumerate(st.session_state.chat_history):
            if i % 2 == 0:
                st.write(f"*User:* {message.content}")
            else:
                st.write(f"*Bot:* {message.content}")
    else:
        st.warning("Please process the documents first.")

# Main function to run the Streamlit app
def main():
    load_dotenv()
    st.set_page_config(page_title="Chat with multiple PDFs", page_icon=":books:")

    if "conversation" not in st.session_state:
        st.session_state.conversation = None
    if "chat_history" not in st.session_state:
        st.session_state.chat_history = None

    st.header("Chat with multiple PDFs :books:")
    user_question = st.text_input("Ask a question about your documents:")
    if user_question:
        handle_userinput(user_question)

    with st.sidebar:
        st.subheader("Your documents")
        pdf_docs = st.file_uploader(
            "Upload your PDFs here and click on 'Process'", accept_multiple_files=True
        )
        if st.button("Process"):
            with st.spinner("Processing..."):
                raw_text = get_pdf_text(pdf_docs)
                text_chunks = get_text_chunks(raw_text)
                vectorstore = get_vectorstore(text_chunks)
                st.session_state.conversation = get_conversation_chain(vectorstore)

if __name__ == '__main__':
    main()